用户质疑 Intelligence Index v5 排名失真
一位用户看完 Intelligence Index v5 后认为排名与实测体验不符，点名 Gemini 4 Argon、Muse Wonder Full 与 GPT-6.1 Sol 的位次可疑，质疑榜单公信力。
Artificial Analysis Intelligence Index V5 launched today. Now the OpenAI models has moved front in the line. And the Fable 5.1 is beaten by Gemini 4 Argon , Muse Wonder Full , Even GPT 6.1 SOL. Which is Not at all True! And GPT 6.1 sol is NO where close to claude Sonnet 5.5 and this says it beats it. Now this looks so different from yesterday and i feel like they are not in a right order based on my experience and also it feels like the Integrity of this Index is Fading out. These are my thoughts if you feel anything different then mention it in the comments.
这条是引用着另一条写的：「Artificial Analysis 发布 Intelligence Index v5，GPT-6 Astra 排第二」